Random Forest Regression for Magnetic Resonance Image Synthesis

By Amod Jog, A. Carass, Snehashis Roy, Dzung L. Pham, Jerry L Prince. 2016

213 citations recorded by the source corpus.

&NA; By choosing different pulse sequences and their parameters, magnetic resonance imaging (MRI) can generate a large variety of tissue contrasts. This very flexibility, however, can yield inconsistencies with MRI acquisitions across datasets or scanning sessions that can in turn cause inconsistent automated image analysis. Although image synthesis of MR images has been shown to be helpful in addressing this problem, an inability to synthesize both T2‐weighted brain images that include the skull and FLuid Attenuated Inversion Recovery (FLAIR) images has been reported. The method described herein, called REPLICA, addresses these limitations. REPLICA is a supervised random forest image synthesis approach that learns a nonlinear regression to predict intensities of alternate tissue contrasts given specific input tissue contrasts. Experimental results include direct image comparisons between synthetic and real images, results from image analysis tasks on both synthetic and real images, and comparison against other state‐of‐the‐art image synthesis methods. REPLICA is computationally fast, and is shown to be comparable to other methods on tasks they are able to perform. Additionally REPLICA has the capability to synthesize both T2‐weighted images of the full head and FLAIR images, and perform intensity standardization between different imaging datasets. HighlightsWe describe an MRI image synthesis algorithm capable of synthesizing full‐head T2w images and FLAIR images.Our algorithm, REPLICA, is a supervised method and learns the nonlinear intensity mappings for synthesis using innovative features and a multi‐resolution design.We show significant improvement in synthetic image quality over state‐of‐the‐art image synthesis algorithms.We also demonstrate that image analysis tasks like segmentation perform similarly for real and REPLICA‐generated synthetic images.REPLICA is computationally very fast and can be easily used as a preprocessing tool before further image analysis. Graphical abstract Figure. No caption available.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, background): ““an intensity transformation applied to a given set of input images to generate a new image with a specific tissue contrast” [199].”
Multimodal MR Synthesis via Modality-Invariant Latent Representation (2017, methodology): “Regression Ensembles with Patch Learning for Image Contrast Agreement (REPLICA) : Our ﬁnal baseline method is REPLICA [9], a supervised random forest image synthesis approach which uses multi-scale features to achieve accurate synthesis results.”
Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks (2018, methodology): “Nonlinear mappings are learned on training data via techniques such as nonlinear regression [8], [9], [23] or location-sensitive neural networks [19].”
Artificial intelligence and machine learning for medical imaging: A technology review. (2021, unknown): “Regarding other tasks where RFs were among the state-of-the-art methods a few years ago, like image synthesis [148 – 150] or segmentation [151,152], the community has now fully switched the attention to CNNs [5,153,154].”
Longitudinal multiple sclerosis lesion segmentation: Resource and challenge (2017, background): “Predicting entire neighborhoods gives further context information such as the presence of lesions predominantly inside WM, which has been shown to improve patch based methods (Jog et al., 2017).”